Skip to content
Private beta

Cybersecurity answers you can check

Lattice is a read-only graph of public cybersecurity knowledge: CVEs, CISA’s exploited list, ATT&CK techniques, weaknesses and detection rules, cross-linked. The difference from a search tool is on every link: whether a source stated it, or we inferred it. Use it from a chat, from your AI agent, from the command line or from a desk of notes.

Four ways in

SOC and IT security teams

Lattice Analyst

Paste an alert, an email, logs or CVE ids, or ask about one.

It answers with a label, the reasons, the techniques the text shows and what to check next, and a person decides. A query plan lists every call it made.

Open the Analyst

AI agents and the people who build them

Lattice MCP

Seven read-only tools over the graph, for Claude, Cursor and any MCP client.

Look up an id, follow the links and report where each came from. Looking up an id and reading a node need no key.

Connect an agent

IT admins and security engineers

lattice-scan

Compare this machine, or a project folder, with what CISA lists as exploited.

Open source command line tool and a Claude skill. Each match is a candidate for you to check. Only CVE ids leave the machine.

Which way in fits your job

Anyone who needs one CVE, today

Triage desk

Search every note by CVE, product, weakness or technique.

Our technical analyses of exploited CVEs, with CISA's deadline. For an id with no note, the record the graph holds.

Open the Triage desk
For SOC specialists

The Lattice Analyst: an assistant that shows its work

Facts, labels and structure are written in code from the graph. A local language model words the explanation, and the answer is checked against the evidence before you see it. It gives a label with the reasons so you can act or escalate, and it never says “safe”. Each answer lists what is missing, and containment steps are suggestions for a person to approve.

Alert triage in the Lattice Analyst: a Contain now label with reasons, and the techniques the pasted text shows
An alert pasted into the Analyst (synthetic input): a label, the reasons, and the technique behind each finding.

The tasks an analyst repeats every day

The query plan for a CVE question: graph calls with their time, a code step that works out the facts, one model call and a check of the answer
The query plan: every graph call, code step and model call with its time.
The evidence pane: the CISA known-exploited record and the NVD entry, each with why it is there and its distance from the question
The evidence pane: the nodes the answer rests on, and why each is there.

It does not connect to your SIEM or scan your network. It works on what you paste and on public data, so it cannot tell you whether you are affected, exploited or covered by a rule. Open it on a phone or a desk; it follows the light or dark theme and can be installed as an app. Open the Lattice Analyst.

For IT admins

lattice-scan: check a host or a project

Apache-2.0licensed command line tool. It reads CISA’s exploited list through Lattice and compares it with the packages, containers, hardware and kernel of the machine it runs on, or with the dependencies a project folder declares. It prints evidence for you to read, and each match is a candidate, not a finding that anything is vulnerable. lattice-scan posture adds what the host exposes and runs. Only CVE ids leave the machine; the inventory is never sent.

pip install lattice-scan
lattice-scan                       # today's exploited list against this machine
lattice-scan --cve CVE-2021-44228  # one CVE

The Claude Code skill runs the same check from a chat on the machine Claude runs on (/plugin marketplace add namiq-ai/lattice-scan). A signed apt repository is at the connection guide; the code is at GitHub. The licence covers the tool, not the Lattice service or the data behind it.

Guides by role

AI agents and the people who build them

An agent that says "likely" instead of "is".

Every link carries a source, a confidence figure and a basis, so your agent can report what a source stated and what was inferred. Discovery needs no key.

Teach your agent to say likely

SOC analysts

Four questions for any new CVE.

Which techniques are associated with it, who said so, which detections exist, and what the graph does not know. The gaps are part of the answer.

A CVE, an agent, and four questions

CIOs and security leaders

Five questions before an agent relies on security reference data.

Your people may already ask assistants about CVEs. The questions apply to any vendor, and the guide answers each one for Lattice, including the parts that are not flattering.

Five questions to ask first

What an answer looks like

How it fits with what we already do

Lattice is reference knowledge. It does not look at your systems. These are the pieces that do, and the reading that goes with them.

What it is not

It does not look at your systems, find anything in them, or tell you what to fix. It is reference material, it can be wrong or out of date, and inferred links are guesses. It is a test of an unfinished service: it comes as is, with no warranty, no uptime promise and no promise it will continue. Read the beta terms before you ask.

Guides

Reference for the Lattice MCP cybersecurity server

Which way in fits your job, the tools and their exact arguments, how to connect each client, and when a graph is the wrong choice.

Get a trial key

Trial keys are issued automatically to the email address you give, with the server address. They have usage limits, expire, and can be withdrawn at any time. When you reach a limit you can verify your account to triple it. For unlimited or commercial use, contact [email protected].

One or two sentences: the agent or tool, and the question you want it to answer. Do not include secrets or customer data.

By requesting a trial key you agree to the Lattice beta terms. The service is provided as is, with no warranty, no service level and no promise of continuity, and NamiQ has no liability for your business. Trial keys have usage limits. Read the terms (opens in a new tab). If you do not open them, they are shown before your key is issued.

Lattice beta terms

Version lattice-beta-2026-11-09.1 · Last updated 9 November 2026. Read them, then press Accept to get your key.

1. What this is

Lattice is a read-only knowledge graph of public cybersecurity information, offered to software and AI agents through an interface called the Model Context Protocol (MCP) and through a web API. It is operated by NamiQ LLC, a Texas limited liability company ("NamiQ", "we", "us").

These terms are the agreement between NamiQ and the person or organisation requesting access ("you"). They apply to the Lattice private beta, including the server, any API key we give you, and everything the service returns (the "Service").

2. It is a beta

The Service is a pre-release test. It can change, break, return different answers from one day to the next, or be withdrawn, at any time and for any reason.

We have made no promise to release a final version, to keep any feature, to offer it free of charge, or to offer it at all after the beta. If we launch a commercial version it will come with its own terms, which you will need to accept separately. Nothing in these terms gives you a right to a commercial plan, a price, or a particular price.

3. Accepting these terms

By requesting a trial key, or by using one, you agree to these terms. You do not have to tick a box to start a trial. To raise the limits you will be asked to verify your account and accept these terms explicitly; we record the version, the date and time, and the details you give.

You confirm that you are at least 18, that you are acting for a business or in a professional capacity, and that you have the authority to accept these terms for the organisation you name. These terms are not intended for consumers.

4. Access and API keys

Trial keys are issued automatically to the email address you give, with no review. A trial key is a trial: it expires on the date we state, and issuing one is not a promise of any later access. We may refuse a request or stop issuing keys at any time, without giving a reason.

A trial key has usage limits. When you reach them you can verify your account (your name, position, company and what you will use the Service for) and accept these terms to raise them. For unlimited or commercial use, contact [email protected].

A key is for you and your organisation only. Keep it secret, do not share it or sell access to it, and tell us at once if it leaks. You are responsible for everything done with your key, including by software or AI agents you connect it to.

We may apply rate limits, change them, suspend a key, or revoke a key at any time, with or without notice, and without liability to you.

5. What you may and may not do

You may use the Service for your own internal security work, research and product development, and you may quote individual results in your own work, provided you keep the attribution notices the Service returns.

You may not: copy, mirror or rebuild the graph or a substantial part of it; retrieve it in bulk by automated enumeration, including by walking identifiers or following links systematically; resell, sublicense or republish the data in bulk; get around rate limits, retrieval limits or access controls, including by holding several keys for one organisation; probe, overload or attack the Service; use it to harm anyone, or to break any law; use it to build a competing dataset or service; or use its output to train, fine-tune or evaluate a model or system that you offer to others, or to build a dataset. Using answers as context for your own agent is allowed.

We apply limits on how much you can ask for per hour and per day, and on how much of the graph one organisation can retrieve. We may change them at any time and we enforce them automatically. The Service is for answering questions, not for extracting data.

Do not send us personal data, secrets or confidential information in your queries. The Service only needs public identifiers such as a CVE number or an ATT&CK technique id.

6. Third-party content

The graph is compiled from public sources owned by other people, including MITRE (ATT&CK and CWE), the U.S. National Vulnerability Database, and open detection-rule projects. Each source has its own licence and attribution requirements. We return the notices that apply to each answer, and you must follow them when you reuse the content.

We do not own third-party content and we do not promise that we are entitled to pass it on in every jurisdiction or for every use. If a source owner or a court asks us to remove content, we may do so immediately.

Links the graph labels as inferred are our own derived guesses, not statements by the source. Any confidence figure attached to them is a ranking aid. It is not a probability, and it has not been validated against real outcomes.

7. No professional advice and no reliance

The Service is information, not advice. It can be incomplete, wrong or out of date. It does not find vulnerabilities, incidents or attackers in your systems, and it does not tell you that you are safe.

You must not rely on the Service as the only basis for any security, safety, legal, compliance, financial or business decision, and you must not use it in any system where a wrong answer could injure a person or cause serious loss. You are solely responsible for your own systems, your own decisions, and what you tell your own customers.

Treat everything the Service returns as untrusted text. It comes from third parties and may contain instructions or claims that are false. If you connect an AI agent, you are responsible for how that agent uses it.

8. No warranty

THE SERVICE IS PROVIDED "AS IS" AND "AS AVAILABLE", WITH ALL FAULTS. TO THE FULLEST EXTENT THE LAW ALLOWS, NAMIQ DISCLAIMS ALL WARRANTIES OF ANY KIND, EXPRESS, IMPLIED OR STATUTORY, INCLUDING WARRANTIES OF ACCURACY, COMPLETENESS, MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, NON-INFRINGEMENT, AND THAT THE SERVICE WILL BE SECURE, UNINTERRUPTED OR ERROR-FREE.

9. No service level, support or continuity

We make no commitment about availability, speed, response times, support, backups, data retention, compatibility between versions, or how long the Service or your access will last. We may modify, suspend or end the Service, or any part of it, at any time, with or without notice. We have no duty to keep your key, your request history, or any data.

Do not build anything you cannot afford to lose on top of the Service during the beta.

10. Limit of liability

TO THE FULLEST EXTENT THE LAW ALLOWS, NAMIQ AND ITS MEMBERS, OFFICERS, EMPLOYEES, CONTRACTORS AND SUPPLIERS WILL NOT BE LIABLE FOR ANY INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL, EXEMPLARY OR PUNITIVE DAMAGES, OR FOR ANY LOSS OF PROFITS, REVENUE, DATA, BUSINESS, CUSTOMERS OR GOODWILL, OR FOR ANY SECURITY INCIDENT, BREACH, MISSED OR FALSE FINDING, OR INTERRUPTION AFFECTING YOUR SYSTEMS OR YOUR BUSINESS, HOWEVER CAUSED AND UNDER ANY THEORY OF LIABILITY, EVEN IF WE HAVE BEEN TOLD IT MAY HAPPEN.

THIS LIMIT APPLIES EVEN WHERE THE LOSS IS CAUSED BY OUR OWN NEGLIGENCE. OUR TOTAL LIABILITY FOR ALL CLAIMS RELATING TO THE SERVICE WILL NOT EXCEED ONE HUNDRED U.S. DOLLARS (US$100).

Nothing in these terms limits liability for fraud, gross negligence or wilful misconduct. Where a law does not allow a limit, that limit applies only as far as the law permits, and nothing here limits liability that cannot be limited by law.

11. Your business is your responsibility

NamiQ has no responsibility for your business, your customers, your products, your contracts or the claims you make to others. Using the Service does not make NamiQ your supplier, partner, adviser or agent, and you must not say or imply that NamiQ endorses you, your product or your results.

12. Your indemnity

YOU WILL DEFEND AND INDEMNIFY NAMIQ AGAINST ANY THIRD-PARTY CLAIM, AND THE LOSSES AND REASONABLE COSTS THAT COME WITH IT, TO THE EXTENT IT ARISES FROM YOUR BREACH OF THESE TERMS OR OF THE LAW, OR FROM YOUR BUSINESS OR PRODUCTS.

13. Ownership and feedback

We keep all rights in the Service, in our own selection and arrangement of the data, and in anything we derive. During the beta you get a limited, revocable, non-exclusive, non-transferable right to use the Service under these terms.

If you give us feedback or ideas, we may use them for any purpose without payment or credit. You are not required to give any.

14. What we log

To run the Service, keep it secure and understand how it is used, we log each request: which tool or endpoint, the public identifiers asked about, the time taken and the result size, the name and version your client reports, your key identifier, and a salted one-way hash of your network address. We do not store your raw address in these logs. We use the logs for operations, abuse prevention and analytics. We keep request logs for 60 days and then delete them. We keep the record of a key, including the terms you accepted and the details you gave to verify your account, for six months after the key expires or is withdrawn, and then delete it. If you ask us to delete your details, we also revoke your Lattice key and delete its records. The privacy page describes how we handle the details you give us on the request form.

Item checks. Some tools check one item at a time, for example a product or package name with its version and sometimes the package system and the operating-system family and number, or a fixed signal code. You may send items only through the tools we provide and only items you are entitled to share; do not send a name or version that identifies a person or a confidential system, such as an internal project name. We do not link an item to your key, your network address or the time of day. We count each item anonymously per day and use the counts, and statistics built from them, to understand what people check and for our own reports. A published statistic shows an item only when many users asked about it. A result is a lead for a person to read, not a statement that a system is or is not vulnerable.

15. Laws and sanctions

You will comply with all laws that apply to your use, including export control and sanctions rules. You confirm that you are not located in, or ordinarily resident in, a country or region under comprehensive U.S. sanctions, and are not on a U.S. restricted-party list.

16. Ending these terms

Either of us may end these terms at any time. We may end or suspend your access immediately if we believe you have broken them. When they end, you must stop using the Service and delete your key. Sections 5 to 15, 16 and 18 continue after they end.

17. Changes to these terms

We may change these terms. We will post the new version on this page with a new version number and date, and we may email the address you gave us. If you keep using the Service after a change you accept the new version. If you do not agree, stop using it.

18. Governing law, disputes and the rest

These terms are governed by the laws of the State of Texas, without regard to its conflict-of-laws rules. Before starting a claim, each of us will try in good faith for 30 days to resolve it informally by writing to the other. Any claim that cannot be resolved that way must be brought in the state or federal courts located in Travis County, Texas, and each of us accepts those courts.

These terms are the whole agreement about the Service and replace anything said before. If a part is unenforceable, the rest still applies. A failure to enforce a right is not a waiver of it. You may not transfer your rights under these terms without our written consent; we may transfer ours. Neither of us is liable for delay caused by events beyond our reasonable control. Nothing here creates a partnership, joint venture, agency or employment relationship.

19. Contact

Questions about these terms, takedown requests, security reports, and unlimited or commercial use: [email protected].